The ScreenTrustCAD study conducted at Karolinska Institutet in Stockholm has shown that artificial intelligence (AI) can more effectively identify breast cancer in screening mammography than traditional methods involving two radiologists.
The study, which involved over 55,500 women aged between 40 and 74, found that a single radiologist supported by AI could detect more cancer cases, increase efficiency, and reduce the rate of false positives compared to the conventional dual-radiologist approach.
Traditionally, breast cancer screening via mammography involves two radiologists reading each exam. The researchers compared this conventional method to a new approach where a single radiologist is aided by AI software.
The traditional dual-radiologist approach detected 250 cancers, while a single radiologist plus AI detected 261, and AI alone found 246.
According to the study, AI’s performance was “statistically non-inferior” to the dual-radiologist method.
The research also found that the use of AI reduced the image-reading time for radiologists by half and cut down on false positives—leading to less unnecessary distress and cost.
Implications
“AI and humans perceive images differently, which creates a synergy that improves our chances of detecting cancer,” said Karin Dembrower, the first author of the study.
Fredrik Strand, the study’s principal investigator, stated, “It’s clear to us that for screening mammography, one AI-supported radiologist is a better alternative than two radiologists without AI.”
The study concluded that AI is now ready to be “controlled implemented” in screening mammography.
However, experts warn that the chosen AI system must be rigorously tested on images from the same type of mammography equipment and continuously monitored post-implementation.
Starting June 2023, AI-supported radiologists have been assessing screening mammograms at Capio St Göran’s Hospital, freeing up more time for the medical staff to focus on cancer patients.
Takeaway
The ScreenTrustCAD study adds to a growing body of evidence supporting the use of AI in healthcare, particularly in cancer detection.
The improved efficiency and effectiveness offered by AI could revolutionize the way breast cancer screenings are conducted, making them faster, more accurate, and potentially more accessible for patients.
If you care about cancer risk, please read studies that exercise may stop cancer in its tracks, and vitamin D can cut cancer death risk.
For more information about cancer, please see recent studies that yogurt and high-fiber diet may cut lung cancer risk, and results showing that new cancer treatment may reawaken the immune system.
The research findings can be found in The Lancet Digital Health.
Follow us on Twitter for more articles about this topic.
Copyright © 2023 Knowridge Science Report. All rights reserved.
